rjmalagon/gemma-3:12b-it-q6

rjmalagon/ gemma-3:12b-it-q6_K

220 Downloads Updated 10 months ago

Bfloat16 version of the Gemma 3 12B and 27b model

vision

ollama run rjmalagon/gemma-3:12b-it-q6_K

curl http://localhost:11434/api/chat \
  -d '{
    "model": "rjmalagon/gemma-3:12b-it-q6_K",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='rjmalagon/gemma-3:12b-it-q6_K',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'rjmalagon/gemma-3:12b-it-q6_K',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 10 months ago

10 months ago

7a3dc67f841b · 11GB ·

model

archgemma3

parameters12.2B

quantizationQ6_K

11GB

license

Gemma Terms of Use Last modified: February 21, 2024 By using, reproducing, modifying, distributing,

8.4kB

params

{ "stop": [ "<end_of_turn>" ] }

37B

template

{{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 }} {{- if or (eq .Rol

358B

Readme

Bfloat16 version of the Gemma 3 12B and 27b model. Requires Ollama >v0.6.0 and BF16 supporting GPU (native or BF16 to FP32 on the fly llama.cpp conversion).

Includes the vision component.

Full model info at https://ollama.com/library/gemma3 , https://huggingface.co/google/gemma-3-27b-it and https://huggingface.co/google/gemma-3-12b-it